Sound and audio is a fundamental aspect of our everyday lives. We create or listen to musical sounds for pleasure or relaxation; we are informed or entertained by speech and music on radio or TV; and sounds from the real world can tell us what is happening around us.
This Audio Day brings together researchers and collaborators engaged in audio-related research projects linked to the University of Surrey, including projects on musical audio repurposing using source separation; spatial audio in the home; making sense of sounds; and creative commons audio. Many of these are collaborative projects, including members of the Centre for Vision, Speech and Signal Processing (CVSSP), Institute of Sound Recording (IoSR), Digital World Research Centre (DWRC) and Centre for Digital Economy (CoDE) at Surrey, plus many other partners including the University of Salford, the University of Southampton, BBC R&D, and Audio Analytic.
To open the Audio Day, we are particularly pleased to welcome Philip Nelson, Executive Chair of EPSRC, as our Keynote Speaker. The Day will include a wide range of talks from members of several of these groups and partners, plus the chance to find out more in posters and demos, an opportunity to network over lunch, and will end with a panel discussion on future directions for audio-related research.
Rik Medlik Building
University of Surrey
Guildford, Surrey GU2 7XH
For directions to the campus, see:
University of Surrey: How to get here
The Rik Medlik Building is building 22 on the Campus Map
10:00 – 10:30 Registration / Coffee
10:30 – 11:10   Keynote
EPSRC, the UK research landscape, and audio engineering research
Philip Nelson (Executive Chair, EPSRC)
11:10 – 11:35   Musical Audio Repurposing using Source Separation
Audio source separation using deep learning techniques
Emad M. Grais, Mark Plumbley (University of Surrey)
Application of source separation for musical audio repurposing and its perceptual effects
Ryan Cheungeun Kim, Phil Coleman, Russell Mason (University of Surrey)
11:35 – 12:10   S3A: Future Spatial Audio in the Home
Introduction to S3A
Phil Coleman (University of Surrey)
Deep Learning for Speech Separation
Qingju Liu (University of Surrey)
Still grumbling about mumbling? Personalisation of Object Based Audio for People with Hearing Impairments
Ben Shirley (University of Salford)
Immersive spatial audio with orchestrated devices
Jon Francombe (BBC R&D)
12:10 - 12:20 Noise Acoustics: Transport Noise
Abigail Bristow (University of Surrey)
12:20   Posters and Demos (Closes 13:30)
Titles, Authors, Abstracts and Locations
13:10   Lunch and Networking
14:00 – 14:10   UK Acoustics Network
Kirill Horoshenkov (University of Sheffield)
14:10 – 14:45   Making Sense of Sounds
Audio Event Detection and Scene Analysis
Mark Plumbley, Yong Xu, Qiuqiang Kong, Wenwu Wang, Philip Jackson (University of Surrey)
Sentimental Audio Memories
David Frohlich, Tijs Duel (University of Surrey)
Artificial Audio Intelligence: an area of technological and commercial leadership for the UK
Sacha Krstulovic (Audio Analytic)
14:45 – 15:10   AudioCommons: Bringing Creative Commons Audio Content to the Creative Industries
Introduction to AudioCommons
Wenwu Wang, Russell Mason, Tim Brookes, Mark Plumbley (University of Surrey)
Timbral attributes for sound effects
Andy Pearce, Russell Mason, Tim Brookes (University of Surrey)
Predicting the perceived level of reverberation using machine learning
Saied Safavi, Wenwu Wang, Mark Plumbley (University of Surrey)
15:10 - 15:20 Audio-Visual Spatial Coherence
Hanne Stenzel (University of Surrey)
15:20 – 15:40   Tea / Coffee
15:40 – 16:30   Panel Discussion: Future Directions for Audio Research
16:30   Closing Remarks